phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 20:13:07 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

refactor get_max_tokens and build_options

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-10-23 19:11:04 -07:00
parent 5965ef3979
commit 4a073fcee5
7 changed files with 33 additions and 38 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -29,9 +29,9 @@ class OpenAICompatCompletionResponse(BaseModel):
choices: List[OpenAICompatCompletionChoice]
def get_sampling_options(request: ChatCompletionRequest) -> dict:
def get_sampling_options(params: SamplingParams) -> dict:
options = {}
if params := request.sampling_params:
if params:
for attr in {"temperature", "top_p", "top_k", "max_tokens"}:
if getattr(params, attr):
options[attr] = getattr(params, attr)